Python 爬取喜马拉雅免费相声音频

qiuyouzhi

from requests import get
from lxml import etree
import os
try:
    os.mkdir("Video")
    os.chdir("Video")
except:
    os.chdir("Video")

def open_url(url):
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'}
    res = get(url, headers=headers)
    return res

def get_xs(res):
    temp = 'https://www.ximalaya.com/xiangsheng'
    html = etree.HTML(res.text)
    name = html.xpath("//*[@class='general-album-list']/div[@class='content']/ul/li/div/a/span/text()")
    href = [temp + each for each in html.xpath("//*[@class='general-album-list']/div[@class='content']/ul/li/div/a[1]/@href")]
    i = 1
    result = {}
    for k in zip(name, href):
        result[i] = k
        i += 1
    return result

def get_Videourl(nm, hf):
    res = open_url(hf)
    vdurl = []
    temp = 'https://www.ximalaya.com/xiangsheng'
    html = etree.HTML(res.text)
    href = html.xpath('//*[@class="sound-list _Qp"]/ul/li/div[2]/a/@href')
    name = html.xpath('//*[@class="sound-list _Qp"]/ul/li/div[2]/a/span/text()')
    ids = [each[-9:] for each in html.xpath('//*[@class="sound-list _Qp"]/ul/li/div[2]/a/@href')]
    # for nm, hf in zip(name, href):
    #     print(nm, ':', temp + hf)
    for id in ids:
        vdurl.append('https://www.ximalaya.com/revision/play/v1/audio?id=%s&ptype=1' % id)
    return vdurl, name

def get_Video(vdurl, nm):
    i = 0
    for url in vdurl:
        res = open_url(url).json()
        for each in res:
            if type(res[each]) != int:
                tempurl = res[each]['src']
                video = open_url(tempurl)
                filename = f"{nm[i]}.m4a"
                print("正在下载：",filename)
                print(i)
                with open(filename, 'wb') as f:
                    f.write(video.content)
        i += 1

def main():
    url = 'https://www.ximalaya.com/xiangsheng/xiangsheng/mr132t2722/'
    res = open_url(url)
    result = get_xs(res)
    for i in result:
        for nm in result[i]:
            print(i, end = ' ')
            print(nm)
            break

    choice = int(input("请选择您要听的专辑序号："))
    nm, hf = result[choice]
    vdurl, nm = get_Videourl(nm, hf)
    get_Video(vdurl, nm)


if __name__ == "__main__":
    main()

我待会把思路发出来，顺便说几个缺陷:

1,翻页没有写

2，爬取相声数量太少

这些我都会一一改进，如果有好的建议，请回复我，谢谢

_2_

沙发！
支持楼主！

liuzhengyuan

付费音频的能爬吗

qiuyouzhi

liuzhengyuan 发表于 2020-5-1 16:48
付费音频的能爬吗

前提我得有个VIP的账号

李子豪

支持一波

wuqramy

应该是免费的都能爬吧

qiuyouzhi

wuqramy 发表于 2020-5-4 17:38
应该是免费的都能爬吧

是的